Modelling soybean yield for the early prediction in the Russian Far East using remote sensing data

Abstract

The paper presents an assessment of the model for predicting soybean yield at the level of municipalities in the Far East for the Oktyabrskiy and Leninskiy districts of the Jewish Autonomous Region, as well as the Khabarovsk and Vyazemskiy districts of Khabarovsk Territory. The share of soybean in the total arable land structure of these municipalities in 2018 ranged from 58% to 97%. According to 2010–2018 data, regression models were constructed for each region. The model used statistical data on district soybean yield, as well as data from remote sensing of the Earth. The values of the maximum NDVI (Normalized Difference Vegetation Index) of arable land and the growing duration at the week that reached maximum NDVI were used as independent variables in the regression model. We used weekly NDVI composites obtained for delineated arable lands through the Vega-Science system. According to long-term observations, it was found that in the study area the maximum NDVI was reached in weeks 30–33 (end of July to mid-August). The RMSE for different regions ranged from 0.06 to 0.15 t/ha, and the MAPE did not exceed 10%. The developed model can be used for predicting soybean yield and planning export operations by farms and territorial authorities.

Application of LAI and NDVI to model soybean yield in the regions of the Russian Far East

“…Nowadays, soybean acreage in the Amur Region, Primorskiy Territory, Jewish Autonomous Region, and Khabarovsk Territory exceeds the area of all other crops combined [15]. In previous studies, soybean yield was estimated at the municipal level in the Far East based on remote sensing data, where the maximum NDVI, as well as various meteorological characteristics, were considered as independent predictors [16,17]. At the same time, models based on LAI have not previously been considered for assessing soybean yield in the Russian Far East.…”